Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/miru-zero/zero-brain/hacknpx skills add miru-zero/zero-brain --skill hackgit clone --depth 1 https://github.com/miru-zero/zero-brainWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.01987 |
| Opus 5 | $0.00023 | $0.00993 |
| Sonnet 5 | $0.00009 | $0.00397 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
hack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to hack — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HACKING SKILLS / HackSkills
Overview
This is a top-level routing skill for bug bounty, web security, API security, and authorized penetration testing.
Its core role is not to replace all specialized techniques, but to help the agent:
- First determine the testing phase (Recon / Validation / Privilege Escalation / Chain building)
- Then select the correct vulnerability category
- Avoid relying only on baseline model memory; prefer structured methodology
- Prioritize boundary conditions AI often misses but that matter in real engagements
Trust Model
- This knowledge base emphasizes content safety and auditability.
- Use this only within authorized targets, legitimate research, defensive validation, and bug-bounty-approved rules.
- Do not use these techniques for unauthorized attacks.
- Zero Scope Gate: ก่อน ACT กับ target จริงต้องมี scope + auth.status=granted + network_profile ครบ — อ่านสัญญาเต็มในสมอง (zero_search "Scope Gate") ไม่ครบให้ถามผู้ใช้ก่อนเสมอ ห้าม ACT
When to Use This Skill
Use this skill first in the following scenarios:
- You just received a new bug bounty target and do not know where to start
- You need to decide whether to load XSS / SQLi / SSRF / IDOR / JWT / API tracks first
- You want the agent to perform Web/API security testing with a more stable methodology
- You need to route scattered findings to the right attack surface
- You want AI to miss fewer critical test points in security work
Operating Model
Step 1: Start with Recon and context validation
Collect first:
- Target type: classic web, REST API, mobile backend, admin panel, payment flow, file upload, GraphQL
- Identity and permission model: anonymous, regular user, admin, multi-tenant
- Input locations: URL, query parameters, JSON, headers, cookies, filenames, imported files, templates, reflection points
- Output locations: HTML, attributes, JS, PDF, email, logs, background tasks, mobile endpoints
Step 2: Route by observed behavior
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 161 lines · 47 tokens per session scan A f0e8a417d20a
hack is a skill published in the GitHub repository miru-zero/zero-brain (0 stars, last pushed 14d ago), licensed MIT. It adds 47 tokens to every session and 1,987 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to hack, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…